ybelkada commited on
Commit
a770de8
·
verified ·
1 Parent(s): a5dc8ab

Upload FalconH1ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +68 -0
  2. generation_config.json +10 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FalconH1ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_in_multiplier": 1.0,
8
+ "attention_out_multiplier": 1.0,
9
+ "bos_token_id": 1,
10
+ "dtype": "bfloat16",
11
+ "embedding_multiplier": 0.034423828125,
12
+ "eos_token_id": 11,
13
+ "expansion_factor": 1.5,
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 512,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 768,
19
+ "key_multiplier": 1.0,
20
+ "lm_head_multiplier": 0.078125,
21
+ "mamba_chunk_size": 128,
22
+ "mamba_conv_bias": true,
23
+ "mamba_d_conv": 4,
24
+ "mamba_d_head": 32,
25
+ "mamba_d_ssm": 768,
26
+ "mamba_d_state": 64,
27
+ "mamba_expand": 2,
28
+ "mamba_n_groups": 1,
29
+ "mamba_n_heads": 24,
30
+ "mamba_norm_before_gate": false,
31
+ "mamba_proj_bias": false,
32
+ "mamba_rms_norm": false,
33
+ "mamba_use_mlp": true,
34
+ "max_position_embeddings": 262144,
35
+ "mlp_bias": false,
36
+ "mlp_multipliers": [
37
+ 1.0,
38
+ 1.0
39
+ ],
40
+ "model_type": "falcon_h1",
41
+ "num_attention_heads": 8,
42
+ "num_hidden_layers": 24,
43
+ "num_key_value_heads": 2,
44
+ "num_logits_to_keep": 1,
45
+ "pad_token_id": 0,
46
+ "projectors_bias": false,
47
+ "rms_norm_eps": 1e-05,
48
+ "rope_scaling": null,
49
+ "rope_theta": 100000000000.0,
50
+ "sliding_window": null,
51
+ "ssm_in_multiplier": 1.0,
52
+ "ssm_multipliers": [
53
+ 1.0,
54
+ 1.0,
55
+ 1.0,
56
+ 1.0,
57
+ 1.0
58
+ ],
59
+ "ssm_out_multiplier": 1.0,
60
+ "tie_word_embeddings": true,
61
+ "time_step_floor": 0.0001,
62
+ "time_step_max": 0.1,
63
+ "time_step_min": 0.001,
64
+ "time_step_rank": "auto",
65
+ "transformers_version": "4.57.0",
66
+ "use_cache": true,
67
+ "vocab_size": 32768
68
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 11,
6
+ 228
7
+ ],
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.57.0"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1556cfc66e5a4b49cf1058c1fb02f3ffcfb191304bf9021066d6e0d05f473a44
3
+ size 182304120